249,122 Hits in 4.0 sec

An Automated Adaption of K-means Based Hybrid Segmentation System into Direct Volume Rendering Object Distinction Mode for Enhanced Visualization Effect

Arash Azim Zadeh Irani, Bahari Belaton
2012 2012 Ninth International Conference on Computer Graphics, Imaging and Visualization  
The rendering mode is modified to accommodate masking information generated by a K-means-based hybrid segmentation algorithm.  ...  Ray Casting is a direct volume rendering technique for visualizing 3D arrays of sampled data. It has vital applications in medical and biological imaging.  ...  K-means-based hybrid segmentation design In phase 1.2, a neural network is used to generate cluster centers.  ... 
doi:10.1109/cgiv.2012.14 dblp:conf/IEEEcgiv/IraniB12 fatcat:mo4nrrkk6nc2ncdszarw6r2whu

Multi-feature based transfer function design for 3D medical image visualization

Yi Peng, Li Chen
2010 2010 3rd International Conference on Biomedical Engineering and Informatics  
We compute a multi-feature descriptor for both two-phase clustering and transfer function design.  ...  Multi -feature, statistical analysis, pre-segmentation, transfer function, volume rendering, visualization I. 2 (255,0,0,32) c (bottom left) and 3 (0,0,255,64) c ( bottom middle).  ...  Transfer Function Design After segmentation, each voxel is tagged with a label indicating which cluster it belongs to.  ... 
doi:10.1109/bmei.2010.5639553 fatcat:so2p35xhcveeli4wxmwjkmsd7y

Treatment response assessment of breast masses on dynamic contrast-enhanced magnetic resonance scans using fuzzy c-means clustering and level set segmentation

Jiazheng Shi, Berkman Sahiner, Heang-Ping Chan, Chintana Paramagul, Lubomir M. Hadjiiski, Mark Helvie, Thomas Chenevert
2009 Medical Physics (Lancaster)  
The method then used the fuzzy c-means ͑FCM͒ clustering algorithm followed by morphological filtering for initial mass segmentation.  ...  volume.  ...  Although the initial segmentation volume based on the FCM clustering was significantly different from that extracted by the radiologist, the volume based on the LS͑FCM͒ method did not show a significant  ... 
doi:10.1118/1.3238101 pmid:19994516 pmcid:PMC2773457 fatcat:rdvzaopownhpzey2byhq6igq2u

A Clustering based Transfer Function for Volume Rendering Using Gray-Gradient Mode Histogram

Yisha Lan, Yimin Ding, Xin Luo, Yanzhao Zhang, Chenxi Huang, E.Y.K. Ng, Weihong Huang, Xuezhong Zhou, Jie Su, Yonghong Peng, Zhicheng Wang, Yongqiang Cheng (+1 others)
2019 IEEE Access  
Clustering analysis is carried out based on the spatial information of volume data in the histogram, and the transfer function is automatically generated by means of clustering analysis of the spatial  ...  In this paper, a new approach of the transfer function is proposed based on clustering analysis of gray-gradient mode histogram, where volume data is represented in a two-dimensional histogram.  ...  The flowchart of transfer function design based on histogram clustering analysis is shown in Fig. 1 .  ... 
doi:10.1109/access.2019.2923080 fatcat:lxur3lkpybffvpgfxhnywqwpsi

Modified Dendrogram of High-dimensional Feature Space for Transfer Function Design

Lei Wang, Xin Zhao, Arie Kaufman
2012 IEEE Conference on Visualization, Proceedings of the  
Furthermore, we propose a fast interactive hierarchical clustering (FIHC) algorithm for accelerating the MD computation and supporting the interactive multi-grained TF design.  ...  We introduce a modified dendrogram (MD) (with sub-trees to represent the feature space clusters) and display it in continuous space for multi-dimensional transfer function (TF) design and modification.  ...  Fig. 14 . 14 Direct volume rendering of CT bladder. (a) The volume rendering using MD based method with 7 attributes which shows better segmentation of the bladder.  ... 
pmid:26279612 pmcid:PMC4536829 fatcat:wv25qtmd4fgyhlp3oip3kqgccm

Instance Segmentation of Fibers from Low Resolution CT Scans via 3D Deep Embedding Learning [article]

Tomasz Konopczyński, Thorben Kröger, Lei Zheng, Jürgen Hesser
2019 arXiv   pre-print
We have designed a 3D instance segmentation architecture built upon a deep fully convolutional network for semantic segmentation with an extra output for embedding learning.  ...  object in a volume.  ...  The overlapping instance sub-volumes are then merged into an output volume. currently in use are usually based on hand designed features.  ... 
arXiv:1901.01034v1 fatcat:gyhbpdskdvb57pbsudty36iypq

Visual Object Localization in Image Collections

Yanyun Qu, Han Liu
2011 2011 Sixth International Conference on Image and Graphics  
Firstly, the image is segmented based on a multiple segmentation algorithm.  ...  Secondly, these generated regions are clustered by spectral clustering method to find the category pattern based on the context of the dataset and the saliency.  ...  in the following. 1) Volume We define the volume of the clustering group as the number of segments contained in the group.  ... 
doi:10.1109/icig.2011.123 dblp:conf/icig/QuL11 fatcat:zfclx5gjbvczjggdvbyjlcyxwe


J. Redeker, P. Gebhardt, A.-K. Reichler, E. Türck, K. Dröder, T. Vietor
2020 Proceedings of the Design Society: DESIGN Conference  
For the development of the algorithm, existing techniques of 3D shape segmentation, especially surface-based part segmentation procedures are reviewed and important areas of activities are revealed.  ...  This representation leads to a new way of designing and redesigning parts for the novel hybrid manufacturing concept Incremental Manufacturing (IM).  ...  In particular, volume-based segmentation, skeleton-based segmentation, and surface-based segmentation.  ... 
doi:10.1017/dsd.2020.144 fatcat:doef2g2ntzhrfpwccxezviroia

Relation-Aware Spreadsheets for Multimodal Volume Segmentation and Visualization [chapter]

Lin Zheng, Yingcai Wu, Kwan-liu Ma
2010 Lecture Notes in Computer Science  
In addition, the user can isolate or highlight a feature of interest in a volume based on different modalities, and see the corresponding segmented results.  ...  This paper presents a user directed volume segmentation system.  ...  In our study, we put our emphasis on intelligent visualization and user interface design for multimodal volume segmentation.  ... 
doi:10.1007/978-3-642-15948-0_12 fatcat:sq7bb4egizcvlnzysbtexjcyki

Automated Segmentation of Knee MRI Using Hierarchical Classifiers and Just Enough Interaction Based Learning: Data from Osteoarthritis Initiative [chapter]

Satyananda Kashyap, Ipek Oguz, Honghai Zhang, Milan Sonka
2016 Lecture Notes in Computer Science  
Segmentation performance using the learning-based cost function showed significant reduction in segmentation errors (p< 0.05) in comparison with conventional gradient-based cost functions.  ...  We present a fully automated learning-based approach for segmenting knee cartilage in the presence of osteoarthritis (OA). The algorithm employs a hierarchical set of two random forest classifiers.  ...  Acknowledgments OAI support for providing the MRI volumes and manual segmentation gratefully acknowledged. This research was supported by NIH grant -R01EB004640.  ... 
doi:10.1007/978-3-319-46723-8_40 pmid:28626842 pmcid:PMC5471813 fatcat:mdaj72bmabdx7fble7nomfrjni

Medical volume segmentation using bank of Gabor filters

Adebayo Olowoyeye, Mihran Tuceryan, Shiaofen Fang
2009 Proceedings of the 2009 ACM symposium on Applied Computing - SAC '09  
In this paper, we will present an unsupervised approach for segmenting medical volume images based on texture properties.  ...  The texture properties of the volume data are defined based on spatial frequencies as implemented using a statistical method known as Gabor filters.  ...  The user can interact with the segmented volume by viewing each cluster independently or by viewing all segmented clusters at once.  ... 
doi:10.1145/1529282.1529458 dblp:conf/sac/OlowoyeyeTF09 fatcat:pw7gxmqmr5dlxhwebmexgkrob4

Visualization of medical volume data based on Improved K-means clustering and segmentation rules

Ji Ma, Yazan Ahmad Muad, Jinjin Chen
2021 IEEE Access  
In this paper, we proposed extracting and segmentation techniques based on K-means algorithm that allows the users to segment and enhances single or multiple targets by a single point to view the features  ...  However, it is difficult to distinguish multiple targets by using the 1D TF-based volume visualization.  ...  First, we have designed the target segmentation technique based on K-means clustering algorithm that can segment the targets which have a similar value to the user's interesting target in the volume.  ... 
doi:10.1109/access.2021.3096790 fatcat:ujf3k3szdvautkyolsr4ifaw6e

LOAF: Load and Resource Aware Federation of Multiple Sensor sub-Networks

Sookyoung Lee, Mohamed Younis, Mohammed Alsolami, Meejeong Lee
2020 IEEE Access  
Such superiority is attributed to the energy-centric design principle of LOAF which strives to place a central cluster at the energy balanced center of all segments and based on which the formation of  ...  In the first phase, LOAF computes eG, i.e., an energy-based center of mass, of a set of segments S based on the inter-segment related communication energy which is proportional to traffic volume exchanged  ...  At Samsung, she was a broadband convergence network designer especially focusing on requirements for QoS and IPv6. Dr.  ... 
doi:10.1109/access.2020.3027821 fatcat:53k5ycmhzbhoxo367h4ia6vxcq

Accuracy and Reproducibility of Adipose Tissue Measurements in Young Infants by Whole Body Magnetic Resonance Imaging

Jan Stefan Bauer, Peter Benjamin Noël, Christiane Vollhardt, Daniela Much, Saliha Degirmenci, Stefanie Brunner, Ernst Josef Rummeny, Hans Hauner, Jan Kassubek
2015 PLoS ONE  
Fat volume was quantified directly and by MR imaging using k-means clustering and threshold-based segmentation procedures to calculate accuracy in vitro.  ...  In vivo reproducibility errors for total fat volume of the sleeping infants ranged from 2.6% to 3.4%. Neither segmentation nor sequence significantly influenced reproducibility.  ...  This work is based on the dissertation of Saliha Degirmenci at the Technische Universität München. Author Contributions  ... 
doi:10.1371/journal.pone.0117127 pmid:25706876 pmcid:PMC4338239 fatcat:uhd57el3k5dklkooro6qi2igum

Spectral clustering for TRUS images

Samar S Mohamed, Magdy MA Salama
2007 BioMedical Engineering OnLine  
Methods: The proposed spectral clustering segmentation algorithm is built on a totally different foundation that doesn't involve any function design or optimization.  ...  Conclusion: The proposed spectral clustering segmentation algorithm obtained fast excellent estimates that can give rough prostate volume and location as well as internal gland segmentation without any  ...  On the other hand, the older segmentation methods are mainly: edge base segmentation, texture based segmentation and model based segmentation.  ... 
doi:10.1186/1475-925x-6-10 pmid:17359549 pmcid:PMC1845149 fatcat:isgaikx6cjc5ploee22umlicqq
« Previous Showing results 1 — 15 out of 249,122 results